Back to Overview

Frontier Red Team

The Frontier Red Team stress-tests AI systems to understand the full extent of their current capabilities and anticipate what comes next. We provide evidence-based analysis about AI’s implications for cybersecurity, national security, and autonomous systems.

DateCategoryTitle

Jun 8, 2026Frontier Red Team
Measuring LLMs’ impact on N-day exploits
Jun 3, 2026Frontier Red Team
Mapping AI-enabled cyber threats: Insights from the LLM ATT&CK Navigator
Jun 3, 2026Policy
What we learned mapping a year’s worth of AI-enabled cyber threats
May 22, 2026Frontier Red Team
Measuring LLMs’ ability to develop exploits
Apr 7, 2026Frontier Red Team
Assessing Claude Mythos Preview’s cybersecurity capabilities
Mar 6, 2026Policy
Partnering with Mozilla to improve Firefox’s security
Mar 6, 2026Frontier Red Team
Reverse engineering Claude's CVE-2026-2796 exploit
Feb 5, 2026Frontier Red Team
Evaluating and mitigating the growing risk of LLM-discovered 0-days
Jan 16, 2026Frontier Red Team
AI models are showing a greater ability to find and exploit vulnerabilities on realistic cyber ranges
Jan 14, 2026Frontier Red Team
Finding bugs across the Python ecosystem with Claude and property-based testing